© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45226
    Prev
    Next
    INDEX
    Explanations

    verbs followed by articles or prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     they
    -1.99
     which
    -1.97
     its
    -1.90
     their
    -1.73
     that
    -1.73
     včetně
    -1.70
     gewi
    -1.56
     représentants
    -1.46
     bénévoles
    -1.36
     about
    -1.35
    POSITIVE LOGITS
    5
    1.58
    2
    1.55
    4
    1.52
    3
    1.45
     began
    1.43
    の場合は
    1.41
    Več
    1.41
    8
    1.41
    6
    1.38
     took
    1.34
    Activations Density 0.399%

    No Known Activations